brintos

brintos / linux-shallow public Read only

0
0
Text · 12.8 KiB · b0a519f Raw
329 lines · plain
1===========2Static Keys3===========4 5.. warning::6 7   DEPRECATED API:8 9   The use of 'struct static_key' directly, is now DEPRECATED. In addition10   static_key_{true,false}() is also DEPRECATED. IE DO NOT use the following::11 12	struct static_key false = STATIC_KEY_INIT_FALSE;13	struct static_key true = STATIC_KEY_INIT_TRUE;14	static_key_true()15	static_key_false()16 17   The updated API replacements are::18 19	DEFINE_STATIC_KEY_TRUE(key);20	DEFINE_STATIC_KEY_FALSE(key);21	DEFINE_STATIC_KEY_ARRAY_TRUE(keys, count);22	DEFINE_STATIC_KEY_ARRAY_FALSE(keys, count);23	static_branch_likely()24	static_branch_unlikely()25 26Abstract27========28 29Static keys allows the inclusion of seldom used features in30performance-sensitive fast-path kernel code, via a GCC feature and a code31patching technique. A quick example::32 33	DEFINE_STATIC_KEY_FALSE(key);34 35	...36 37        if (static_branch_unlikely(&key))38                do unlikely code39        else40                do likely code41 42	...43	static_branch_enable(&key);44	...45	static_branch_disable(&key);46	...47 48The static_branch_unlikely() branch will be generated into the code with as little49impact to the likely code path as possible.50 51 52Motivation53==========54 55 56Currently, tracepoints are implemented using a conditional branch. The57conditional check requires checking a global variable for each tracepoint.58Although the overhead of this check is small, it increases when the memory59cache comes under pressure (memory cache lines for these global variables may60be shared with other memory accesses). As we increase the number of tracepoints61in the kernel this overhead may become more of an issue. In addition,62tracepoints are often dormant (disabled) and provide no direct kernel63functionality. Thus, it is highly desirable to reduce their impact as much as64possible. Although tracepoints are the original motivation for this work, other65kernel code paths should be able to make use of the static keys facility.66 67 68Solution69========70 71 72gcc (v4.5) adds a new 'asm goto' statement that allows branching to a label:73 74https://gcc.gnu.org/ml/gcc-patches/2009-07/msg01556.html75 76Using the 'asm goto', we can create branches that are either taken or not taken77by default, without the need to check memory. Then, at run-time, we can patch78the branch site to change the branch direction.79 80For example, if we have a simple branch that is disabled by default::81 82	if (static_branch_unlikely(&key))83		printk("I am the true branch\n");84 85Thus, by default the 'printk' will not be emitted. And the code generated will86consist of a single atomic 'no-op' instruction (5 bytes on x86), in the87straight-line code path. When the branch is 'flipped', we will patch the88'no-op' in the straight-line codepath with a 'jump' instruction to the89out-of-line true branch. Thus, changing branch direction is expensive but90branch selection is basically 'free'. That is the basic tradeoff of this91optimization.92 93This lowlevel patching mechanism is called 'jump label patching', and it gives94the basis for the static keys facility.95 96Static key label API, usage and examples97========================================98 99 100In order to make use of this optimization you must first define a key::101 102	DEFINE_STATIC_KEY_TRUE(key);103 104or::105 106	DEFINE_STATIC_KEY_FALSE(key);107 108 109The key must be global, that is, it can't be allocated on the stack or dynamically110allocated at run-time.111 112The key is then used in code as::113 114        if (static_branch_unlikely(&key))115                do unlikely code116        else117                do likely code118 119Or::120 121        if (static_branch_likely(&key))122                do likely code123        else124                do unlikely code125 126Keys defined via DEFINE_STATIC_KEY_TRUE(), or DEFINE_STATIC_KEY_FALSE, may127be used in either static_branch_likely() or static_branch_unlikely()128statements.129 130Branch(es) can be set true via::131 132	static_branch_enable(&key);133 134or false via::135 136	static_branch_disable(&key);137 138The branch(es) can then be switched via reference counts::139 140	static_branch_inc(&key);141	...142	static_branch_dec(&key);143 144Thus, 'static_branch_inc()' means 'make the branch true', and145'static_branch_dec()' means 'make the branch false' with appropriate146reference counting. For example, if the key is initialized true, a147static_branch_dec(), will switch the branch to false. And a subsequent148static_branch_inc(), will change the branch back to true. Likewise, if the149key is initialized false, a 'static_branch_inc()', will change the branch to150true. And then a 'static_branch_dec()', will again make the branch false.151 152The state and the reference count can be retrieved with 'static_key_enabled()'153and 'static_key_count()'.  In general, if you use these functions, they154should be protected with the same mutex used around the enable/disable155or increment/decrement function.156 157Note that switching branches results in some locks being taken,158particularly the CPU hotplug lock (in order to avoid races against159CPUs being brought in the kernel while the kernel is getting160patched). Calling the static key API from within a hotplug notifier is161thus a sure deadlock recipe. In order to still allow use of the162functionality, the following functions are provided:163 164	static_key_enable_cpuslocked()165	static_key_disable_cpuslocked()166	static_branch_enable_cpuslocked()167	static_branch_disable_cpuslocked()168 169These functions are *not* general purpose, and must only be used when170you really know that you're in the above context, and no other.171 172Where an array of keys is required, it can be defined as::173 174	DEFINE_STATIC_KEY_ARRAY_TRUE(keys, count);175 176or::177 178	DEFINE_STATIC_KEY_ARRAY_FALSE(keys, count);179 1804) Architecture level code patching interface, 'jump labels'181 182 183There are a few functions and macros that architectures must implement in order184to take advantage of this optimization. If there is no architecture support, we185simply fall back to a traditional, load, test, and jump sequence. Also, the186struct jump_entry table must be at least 4-byte aligned because the187static_key->entry field makes use of the two least significant bits.188 189* ``select HAVE_ARCH_JUMP_LABEL``,190    see: arch/x86/Kconfig191 192* ``#define JUMP_LABEL_NOP_SIZE``,193    see: arch/x86/include/asm/jump_label.h194 195* ``__always_inline bool arch_static_branch(struct static_key *key, bool branch)``,196    see: arch/x86/include/asm/jump_label.h197 198* ``__always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)``,199    see: arch/x86/include/asm/jump_label.h200 201* ``void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type)``,202    see: arch/x86/kernel/jump_label.c203 204* ``struct jump_entry``,205    see: arch/x86/include/asm/jump_label.h206 207 2085) Static keys / jump label analysis, results (x86_64):209 210 211As an example, let's add the following branch to 'getppid()', such that the212system call now looks like::213 214  SYSCALL_DEFINE0(getppid)215  {216        int pid;217 218  +     if (static_branch_unlikely(&key))219  +             printk("I am the true branch\n");220 221        rcu_read_lock();222        pid = task_tgid_vnr(rcu_dereference(current->real_parent));223        rcu_read_unlock();224 225        return pid;226  }227 228The resulting instructions with jump labels generated by GCC is::229 230  ffffffff81044290 <sys_getppid>:231  ffffffff81044290:       55                      push   %rbp232  ffffffff81044291:       48 89 e5                mov    %rsp,%rbp233  ffffffff81044294:       e9 00 00 00 00          jmpq   ffffffff81044299 <sys_getppid+0x9>234  ffffffff81044299:       65 48 8b 04 25 c0 b6    mov    %gs:0xb6c0,%rax235  ffffffff810442a0:       00 00236  ffffffff810442a2:       48 8b 80 80 02 00 00    mov    0x280(%rax),%rax237  ffffffff810442a9:       48 8b 80 b0 02 00 00    mov    0x2b0(%rax),%rax238  ffffffff810442b0:       48 8b b8 e8 02 00 00    mov    0x2e8(%rax),%rdi239  ffffffff810442b7:       e8 f4 d9 00 00          callq  ffffffff81051cb0 <pid_vnr>240  ffffffff810442bc:       5d                      pop    %rbp241  ffffffff810442bd:       48 98                   cltq242  ffffffff810442bf:       c3                      retq243  ffffffff810442c0:       48 c7 c7 e3 54 98 81    mov    $0xffffffff819854e3,%rdi244  ffffffff810442c7:       31 c0                   xor    %eax,%eax245  ffffffff810442c9:       e8 71 13 6d 00          callq  ffffffff8171563f <printk>246  ffffffff810442ce:       eb c9                   jmp    ffffffff81044299 <sys_getppid+0x9>247 248Without the jump label optimization it looks like::249 250  ffffffff810441f0 <sys_getppid>:251  ffffffff810441f0:       8b 05 8a 52 d8 00       mov    0xd8528a(%rip),%eax        # ffffffff81dc9480 <key>252  ffffffff810441f6:       55                      push   %rbp253  ffffffff810441f7:       48 89 e5                mov    %rsp,%rbp254  ffffffff810441fa:       85 c0                   test   %eax,%eax255  ffffffff810441fc:       75 27                   jne    ffffffff81044225 <sys_getppid+0x35>256  ffffffff810441fe:       65 48 8b 04 25 c0 b6    mov    %gs:0xb6c0,%rax257  ffffffff81044205:       00 00258  ffffffff81044207:       48 8b 80 80 02 00 00    mov    0x280(%rax),%rax259  ffffffff8104420e:       48 8b 80 b0 02 00 00    mov    0x2b0(%rax),%rax260  ffffffff81044215:       48 8b b8 e8 02 00 00    mov    0x2e8(%rax),%rdi261  ffffffff8104421c:       e8 2f da 00 00          callq  ffffffff81051c50 <pid_vnr>262  ffffffff81044221:       5d                      pop    %rbp263  ffffffff81044222:       48 98                   cltq264  ffffffff81044224:       c3                      retq265  ffffffff81044225:       48 c7 c7 13 53 98 81    mov    $0xffffffff81985313,%rdi266  ffffffff8104422c:       31 c0                   xor    %eax,%eax267  ffffffff8104422e:       e8 60 0f 6d 00          callq  ffffffff81715193 <printk>268  ffffffff81044233:       eb c9                   jmp    ffffffff810441fe <sys_getppid+0xe>269  ffffffff81044235:       66 66 2e 0f 1f 84 00    data32 nopw %cs:0x0(%rax,%rax,1)270  ffffffff8104423c:       00 00 00 00271 272Thus, the disable jump label case adds a 'mov', 'test' and 'jne' instruction273vs. the jump label case just has a 'no-op' or 'jmp 0'. (The jmp 0, is patched274to a 5 byte atomic no-op instruction at boot-time.) Thus, the disabled jump275label case adds::276 277  6 (mov) + 2 (test) + 2 (jne) = 10 - 5 (5 byte jump 0) = 5 addition bytes.278 279If we then include the padding bytes, the jump label code saves, 16 total bytes280of instruction memory for this small function. In this case the non-jump label281function is 80 bytes long. Thus, we have saved 20% of the instruction282footprint. We can in fact improve this even further, since the 5-byte no-op283really can be a 2-byte no-op since we can reach the branch with a 2-byte jmp.284However, we have not yet implemented optimal no-op sizes (they are currently285hard-coded).286 287Since there are a number of static key API uses in the scheduler paths,288'pipe-test' (also known as 'perf bench sched pipe') can be used to show the289performance improvement. Testing done on 3.3.0-rc2:290 291jump label disabled::292 293 Performance counter stats for 'bash -c /tmp/pipe-test' (50 runs):294 295        855.700314 task-clock                #    0.534 CPUs utilized            ( +-  0.11% )296           200,003 context-switches          #    0.234 M/sec                    ( +-  0.00% )297                 0 CPU-migrations            #    0.000 M/sec                    ( +- 39.58% )298               487 page-faults               #    0.001 M/sec                    ( +-  0.02% )299     1,474,374,262 cycles                    #    1.723 GHz                      ( +-  0.17% )300   <not supported> stalled-cycles-frontend301   <not supported> stalled-cycles-backend302     1,178,049,567 instructions              #    0.80  insns per cycle          ( +-  0.06% )303       208,368,926 branches                  #  243.507 M/sec                    ( +-  0.06% )304         5,569,188 branch-misses             #    2.67% of all branches          ( +-  0.54% )305 306       1.601607384 seconds time elapsed                                          ( +-  0.07% )307 308jump label enabled::309 310 Performance counter stats for 'bash -c /tmp/pipe-test' (50 runs):311 312        841.043185 task-clock                #    0.533 CPUs utilized            ( +-  0.12% )313           200,004 context-switches          #    0.238 M/sec                    ( +-  0.00% )314                 0 CPU-migrations            #    0.000 M/sec                    ( +- 40.87% )315               487 page-faults               #    0.001 M/sec                    ( +-  0.05% )316     1,432,559,428 cycles                    #    1.703 GHz                      ( +-  0.18% )317   <not supported> stalled-cycles-frontend318   <not supported> stalled-cycles-backend319     1,175,363,994 instructions              #    0.82  insns per cycle          ( +-  0.04% )320       206,859,359 branches                  #  245.956 M/sec                    ( +-  0.04% )321         4,884,119 branch-misses             #    2.36% of all branches          ( +-  0.85% )322 323       1.579384366 seconds time elapsed324 325The percentage of saved branches is .7%, and we've saved 12% on326'branch-misses'. This is where we would expect to get the most savings, since327this optimization is about reducing the number of branches. In addition, we've328saved .2% on instructions, and 2.8% on cycles and 1.4% on elapsed time.329